Join me for an exciting session where we'll have some fun with Lego SpikePrime Robot and AzureOpenAI. I'm proud to be presenting at Global Azure Sydney 2024 - Microsoft Reactor Sydney @ 20/04/2024.

📌 Session: Fine-tune GPT-3.5 model to control Lego Robot using Azure OpenAI & Python 🗣️ Speaker: Daniel Fang

Session details: https://sessionize.com/view/rjfzv8k0/GridSmart?format=Embed_Styled_Html&isDark=False&title=Global%20Azure%20Sydney%202024 Reserve your spot: https://www.tickettailor.com/events/azuresydneyusergroup/1193113

Recently, I found myself with some free time, and it brought back a memory from our robotics team. I remember one of the girls on the team trying to use ChatGPT to help her write code for our Masterpiece Season mission. She was hoping to get some assistance resolving a tricky problem with our robot. Unfortunately, even though the code it generated looked solid, it didn't run correctly when we tried it out on the robot.

Out of curiosity, I decided to give it a go myself to see what might have gone wrong. Here's an example of a Python snippet that looks fine at first glance:

import hub
from spike import PrimeHub, Motor, MotorPair

hub = PrimeHub()

motor_pair = MotorPair('A', 'B')

motor_pair.start(50, 0)  # Move straight at 50% speed

The syntax is correct, and the code seems reasonable for controlling a Spike Prime robot. But when you upload this code to the robot, something weird happens: the robot doesn't quite behave the way it should. It might not move at all, or it could respond unpredictably.

So, what's going on here?

Well, after some quick troubleshooting, I realized there's a bit more to getting a Spike Prime robot working smoothly than just correct Python syntax. The code must align perfectly with the robot's specific hardware configuration, sensor inputs, and timing mechanisms. It's not just about writing Python - it's about writing the right Python for this context.

Looks like I've got an investigation on my hands. Time to dive deeper into how the Spike Prime API works and figure out why ChatGPT's code, while syntactically correct, doesn't hit the mark. It's a reminder that while AI tools can be incredibly useful, robotics is a nuanced field where hardware, software, and context all come into play.

If I crack the mystery, I'll be sure to share what I learn!

It's here, the National Competition Day for the FLL Masterpiece Season! The excitement was off the charts, and we knew we had to be up bright and early to prepare for this big day. By 8 AM, Team Cleverbots were already at the competition pit in Macquarie University, fully geared up with our robot and our team's contagious energy. The atmosphere was buzzing with teams from all over, each ready for one last epic showdown.

First on our agenda was the Innovation Project presentation. Understandably, the girls were a bit nervous, but they absolutely nailed it! They presented their "Fresh: Hobby Sharing AI App" with enthusiasm, and even when the judges asked tough questions, they handled them like pros. Watching them speak with such confidence was a proud moment for all of us, especially considering the level of competition we were up against.

Then came the Robot Game, and this was where things really heated up. Our robot was performing better than ever, and we had three rounds to prove its capabilities. Each round felt like a new achievement, our score kept rising, and the team was cheering louder with every success. By the end of the day, we hit an incredible 355 points, setting a new personal best! It was a huge moment, and the sense of pride and accomplishment on the kids' faces was priceless after all those long hours of practice.

As the day came to a close, we couldn't help but reflect on the unforgettable season we'd just completed. Not only did we leave with a huge sense of achievement, but we also got a sneak peek at next year's theme. Let me tell you, the new challenge looks just as exciting, maybe even more! We're already buzzing with ideas and can't wait to get started on brainstorming for the upcoming season.

What a journey it has been, from regionals to nationals, from early mornings to late-night practice sessions. And now, we're ready to tackle what's next. Bring on next year's challenge! Our robotics adventure is far from over, so stay tuned!

We are thrilled to share some exciting updates about Fresh, our AI-powered hobby-sharing app. Over the past few months, we've been working tirelessly to enhance your experience by incorporating valuable feedback from tech experts and our vibrant community.

One of the significant improvements is the expansion of our hobby directory. We've added a plethora of new hobbies to ensure that everyone finds something that resonates with their interests. Whether you're into pottery, urban gardening, or drone racing, Fresh has got you covered.

Our chatbot has also received a significant upgrade. It now suggests nearby events based on your current location, making it easier for you to connect with like-minded enthusiasts in your area. Simply tell the chatbot what you're interested in, and it will provide personalized recommendations for events and meetups happening near you.

We've also produced new tutorial videos to help you get the most out of Fresh. These guide you through the app's features and show you how to make the most of our platform.

Moreover, we've made significant strides in enhancing the app's accessibility. Fresh is now fully functional on both desktop and mobile devices, ensuring you can stay connected to your hobbies anytime, anywhere.

We couldn't have achieved these improvements without your invaluable feedback. Thank you for being a part of our journey. The girls are committed to continually enhancing Fresh to make it the best platform for hobby enthusiasts worldwide.

Here we go! It's finally time for the Masterpiece Season's regional competition in Abbotsleigh! The school is sending three teams, and we're proud to be one of them. The anticipation has been building, and the day has finally arrived.

The journey to the venue was smooth, with an easy ride on the train. When we arrived, we were greeted by over 15 teams, all ready to compete. The energy in the room was incredible! You could feel the excitement buzzing as everyone prepared for the big day.

Our team absolutely nailed the Innovation Project presentation. The judges were fully engaged, asking insightful questions, and the girls did a fantastic job presenting their idea: the Fresh: Hobby Sharing AI App. It's designed to help people connect over shared interests, and they explained it with such confidence and passion. I could see how impressed the judges were, and it felt like all our hard work in the weeks leading up to this moment really paid off.

When it came to the Robot Game, we had an incredible start! In the first round, we scored an impressive 285 points, which put us in second place right out of the gate. The kids were ecstatic, and the excitement only grew as the day went on. The robot performed consistently well, and our strategies were really coming together. Throughout the day, we maintained a strong performance, and it felt like everything was clicking into place.

By the end of the competition, we had reason to celebrate big time! We were awarded the Innovation Project Award, a recognition of the team's creativity and hard work on the Fresh app. On top of that, we finished in third place in the Robot Game, a huge accomplishment considering the level of competition we faced.

And the best part? We're going to the national competition again this year! It's such an incredible feeling to see all the dedication and teamwork paying off. The kids are thrilled, and so am I. We're already talking about how to take our ideas to the next level as we prepare for nationals.

It's been an amazing day, and we couldn't be more excited for what's next. National competition, here we come! Stay tuned, this journey is far from over!

We have a plan of attack for our robot game this time! We're aiming to score 300 points if everything works out. But as we know, things just don't always go as planned.

To improve our robot's performance, we've focused a lot on engineering control and handling misalignments during movement. We've prepared code that can handle big errors in movements caused by attachments. By writing robot code that anticipates unexpected situations, we can make on-the-fly adjustments during the game.

Our first template of Python code started to work with lots of help from our coach. We used functions to simplify our robot's movements in coding, which made it easier to manage and debug. Incorporating the gyro sensor has been a game-changer for us, assisting with precise turning and moving.

We've spent countless hours practicing to make every action accurate. Sometimes, we have to redo all the coding just to improve by a few seconds. It's a tedious process, but those few seconds can make a significant difference in the competition.

By focusing on precision and reliability, we're hoping to make our robot more consistent during the game. It's been a challenging process, but we're excited to see how our efforts pay off. Fingers crossed for a successful run!

The team is struggling with writing Python for the first time! It's so hard, and we don't know where to start. Drag-and-drop coding in the code blocks was so easy, but now we need to learn Python and figure out what to do. The Spike Prime has some examples, but they're not so easy to understand for us.

We turned to ChatGPT for help. It does output lots of code, but it doesn't run on the app. Why? We asked our coach for help and learned that the Spike Prime only uses a specific set of Python, and the robot only knows some of the functions but not all.

It turns out that Spike Prime uses MicroPython, which is a simplified version of Python designed for microcontrollers and embedded systems. This means that not all standard Python libraries and functions are available. Some of the code that ChatGPT provides uses functions that the Spike Prime doesn't support.

This was a bit disheartening at first. We thought that learning Python would open up new possibilities, but instead, we hit a wall. However, we realized that this is just another challenge to overcome. We're now focusing on learning the specific commands and functions that are available in Spike Prime's MicroPython environment.

It's still tough, but we're making progress. We're finding tutorials and resources specifically for Spike Prime's Python coding. We're also experimenting with small bits of code to see what works and what doesn't. It's a learning process, and while it's frustrating at times, it's also exciting to see our robot respond to the code we've written.

In the end, we're hopeful that with perseverance and a better understanding of Spike Prime's Python capabilities, we'll be able to code like pros. For anyone else struggling with this, know that you're not alone, and don't hesitate to seek help and keep experimenting!

We've decided to bring our idea to life by building an AI app for hobby sharing called FRESH. The inspiration behind FRESH is to create a platform that helps people find nearby hobbies and workshops where they can learn new things and connect with others who share similar interests.

FRESH isn't just a directory; it's a comprehensive resource with a vast database of hobbies available to assist people in exploring new activities. Whether you're interested in pottery, coding, photography, or any other hobby, FRESH aims to make the search easy and engaging.

What sets FRESH apart is its clever chatbot assistant. Powered by AI technologies like ChatGPT and enriched with a collection of documents we've assembled, the chatbot can communicate with users to understand their likes and preferences. Based on this interaction, it offers personalized hobby suggestions drawn from our extensive backend knowledge base.

The chatbot doesn't just list options; it engages in a conversation to help users discover hobbies they might not have considered. It's like having a friendly guide who's always ready to inspire and inform.

We can't wait to see the potential of FRESH to help people discover new passions and build a community around shared interests. By combining arts, technology, and AI, we're creating an innovative way for people to enrich their lives and connect with others.

We are interested in exploring how AI can help with our research, brainstorming, and feedback. We tried using ChatGPT and DALL·E to generate answers to our questions and to understand the best ways to use these new tools. We also had a lot of fun creating AI-generated images to help us visualize our innovation project.

Using ChatGPT, we were able to brainstorm ideas more efficiently. Whenever we hit a roadblock, we asked ChatGPT for suggestions, and it provided us with fresh perspectives we hadn't considered before. It was like having a collaborative partner available 24/7, ready to help us think through complex problems.

DALL-E, on the other hand, allowed us to bring our ideas to life visually. By inputting descriptions of concepts and scenarios related to our project, DALL-E generated images that captured the essence of our thoughts. This was incredibly helpful during team meetings, as visual aids made it easier for everyone to understand and contribute to the discussion.

One of the most enjoyable parts was creating AI-generated images for our innovation project. Seeing our ideas transformed into visuals not only made the project more tangible but also sparked new ideas and directions to explore. It was fascinating to see how the AI interpreted our descriptions and turned them into creative imagery.

Integrating AI tools like ChatGPT and DALL-E into our learning has significantly enhanced the way we approach education. They've enhanced our research process, made brainstorming sessions more productive, and provided valuable feedback on our ideas. Plus, experimenting with these tools has been both educational and fun.

The FIRST LEGO League (FLL) MASTERPIECE season is upon us, and our team is buzzing with excitement. We're diving into the Innovation Project, where creativity meets technology, and we're eager to explore new ideas that share our hobbies through arts, tech, and AI to create innovative experiences.

This year's theme challenges us to think outside the box and find ways to enhance how people engage with the arts. We've been brainstorming how we can combine our love for robotics, programming, and the arts to make something truly unique.

One idea we're exploring is developing an interactive platform that uses artificial intelligence to connect artists and hobbyists from around the world. Imagine a space where painters, musicians, writers, and tech enthusiasts collaborate on projects, using AI tools to overcome language barriers and distance. AI could assist in translating artistic styles or suggesting creative collaborations based on users' interests.

We're also considering creating a robotic art installation that responds to audience input. Using sensors and AI algorithms, the robot could interpret emotions or movements from viewers and translate them into visual art or music in real-time. This would not only be a captivating experience but also demonstrate the harmony between human expression and technology.

Another concept is an educational app that uses augmented reality to teach art techniques. Users could point their device at a canvas or workspace, and the app would overlay guides, tips, and even demonstrate strokes or notes for instruments. Incorporating AI would personalize the learning experience, adjusting to the user's skill level and providing feedback.

Our goal is to develop a project that not only fulfills the FLL criteria but also brings people together through shared hobbies and artistic expression. By leveraging arts, technology, and AI, we hope to create an innovative solution that inspires creativity and makes the arts more accessible to everyone.

The journey of exploration and innovation is just beginning, and the possibilities are endless.